Complete the code to create a simple neural network layer using Python.
layer_output = input_data [1] weights + biasThe neural network layer multiplies input data by weights before adding bias.
Complete the code to apply an activation function to the neural network output.
activated_output = [1](layer_output)The ReLU function is a common activation that keeps positive values and sets negatives to zero.
Fix the error in the code to calculate the prediction from inputs and weights.
prediction = [1](inputs, weights)The dot product multiplies inputs and weights element-wise and sums them, which is needed for prediction.
Fill both blanks to create a dictionary of squared inputs greater than 5.
result = {x: x[1]2 for x in inputs if x [2] 5}We square each input with '**2' and filter those greater than 5 with '>'.
Fill all three blanks to create a filtered dictionary with uppercase keys and values greater than 10.
filtered = [1]: [2] for [3], [2] in data.items() if [2] > 10
Keys are converted to uppercase with k.upper(), values are v, and iteration uses k for keys.